From 2f685e021dd66d9182c588ffbcc40d518077b0f3 Mon Sep 17 00:00:00 2001 From: Johannes Weiner Date: Wed, 3 Jun 2020 16:02:53 -0700 Subject: [PATCH 2367/2944] mm: base LRU balancing on an explicit cost model task #31256938 commit 1431d4d11abb265e79cd44bed2f5ea93f1bcc57b upstream Currently, scan pressure between the anon and file LRU lists is balanced based on a mixture of reclaim efficiency and a somewhat vague notion of "value" of having certain pages in memory over others. That concept of value is problematic, because it has caused us to count any event that remotely makes one LRU list more or less preferrable for reclaim, even when these events are not directly comparable and impose very different costs on the system. One example is referenced file pages that we still deactivate and referenced anonymous pages that we actually rotate back to the head of the list. There is also conceptual overlap with the LRU algorithm itself. By rotating recently used pages instead of reclaiming them, the algorithm already biases the applied scan pressure based on page value. Thus, when rebalancing scan pressure due to rotations, we should think of reclaim cost, and leave assessing the page value to the LRU algorithm. Lastly, considering both value-increasing as well as value-decreasing events can sometimes cause the same type of event to be counted twice, i.e. how rotating a page increases the LRU value, while reclaiming it succesfully decreases the value. In itself this will balance out fine, but it quietly skews the impact of events that are only recorded once. The abstract metric of "value", the murky relationship with the LRU algorithm, and accounting both negative and positive events make the current pressure balancing model hard to reason about and modify. This patch switches to a balancing model of accounting the concrete, actually observed cost of reclaiming one LRU over another. For now, that cost includes pages that are scanned but rotated back to the list head. Subsequent patches will add consideration for IO caused by refaulting of recently evicted pages. Replace struct zone_reclaim_stat with two cost counters in the lruvec, and make everything that affects cost go through a new lru_note_cost() function. Signed-off-by: Johannes Weiner Signed-off-by: Andrew Morton Acked-by: Michal Hocko Cc: Joonsoo Kim Cc: Minchan Kim Cc: Rik van Riel Link: http://lkml.kernel.org/r/20200520232525.798933-9-hannes@cmpxchg.org Signed-off-by: Linus Torvalds Signed-off-by: zhongjiang-ali Reviewed-by: Xunlei Pang --- include/linux/mmzone.h | 21 +++++++-------------- include/linux/swap.h | 2 ++ mm/memcontrol.c | 18 ++++++------------ mm/swap.c | 19 ++++++++----------- mm/vmscan.c | 40 ++++++++++++++++++---------------------- 5 files changed, 41 insertions(+), 59 deletions(-) diff --git a/include/linux/mmzone.h b/include/linux/mmzone.h index 82e5913..f8ead78 100644 --- a/include/linux/mmzone.h +++ b/include/linux/mmzone.h @@ -237,19 +237,6 @@ static inline bool is_active_lru(enum lru_list lru) return (lru == LRU_ACTIVE_ANON || lru == LRU_ACTIVE_FILE); } -struct zone_reclaim_stat { - /* - * The pageout code in vmscan.c keeps track of how many of the - * mem/swap backed and file backed pages are referenced. - * The higher the rotated/scanned ratio, the more valuable - * that cache is. - * - * The anon LRU stats live in [0], file LRU stats in [1] - */ - unsigned long recent_rotated[2]; - unsigned long recent_scanned[2]; -}; - enum lruvec_flags { LRUVEC_CONGESTED, /* lruvec has many dirty pages * backed by a congested BDI @@ -266,7 +253,13 @@ enum lruvec_flags { struct lruvec { struct list_head lists[NR_LRU_LISTS]; - struct zone_reclaim_stat reclaim_stat; + /* + * These track the cost of reclaiming one LRU - file or anon - + * over the other. As the observed cost of reclaiming one LRU + * increases, the reclaim scan balance tips toward the other. + */ + unsigned long anon_cost; + unsigned long file_cost; /* Evictions & activations on the inactive file list */ atomic_long_t inactive_age; /* Refaults at the time of last reclaim cycle */ diff --git a/include/linux/swap.h b/include/linux/swap.h index ebf20f3..d8a37a8 100644 --- a/include/linux/swap.h +++ b/include/linux/swap.h @@ -332,6 +332,8 @@ struct vma_swap_readahead { /* linux/mm/swap.c */ +extern void lru_note_cost(struct lruvec *lruvec, bool file, + unsigned int nr_pages); extern void lru_cache_add(struct page *); extern void lru_add_page_tail(struct page *page, struct page *page_tail, struct lruvec *lruvec, struct list_head *head); diff --git a/mm/memcontrol.c b/mm/memcontrol.c index 2565c32..31163a9 100644 --- a/mm/memcontrol.c +++ b/mm/memcontrol.c @@ -4408,23 +4408,17 @@ static int memcg_stat_show(struct seq_file *m, void *v) { pg_data_t *pgdat; struct mem_cgroup_per_node *mz; - struct zone_reclaim_stat *rstat; - unsigned long recent_rotated[2] = {0, 0}; - unsigned long recent_scanned[2] = {0, 0}; + unsigned long anon_cost = 0; + unsigned long file_cost = 0; for_each_online_pgdat(pgdat) { mz = mem_cgroup_nodeinfo(memcg, pgdat->node_id); - rstat = &mz->lruvec.reclaim_stat; - recent_rotated[0] += rstat->recent_rotated[0]; - recent_rotated[1] += rstat->recent_rotated[1]; - recent_scanned[0] += rstat->recent_scanned[0]; - recent_scanned[1] += rstat->recent_scanned[1]; + anon_cost += mz->lruvec.anon_cost; + file_cost += mz->lruvec.file_cost; } - seq_printf(m, "recent_rotated_anon %lu\n", recent_rotated[0]); - seq_printf(m, "recent_rotated_file %lu\n", recent_rotated[1]); - seq_printf(m, "recent_scanned_anon %lu\n", recent_scanned[0]); - seq_printf(m, "recent_scanned_file %lu\n", recent_scanned[1]); + seq_printf(m, "anon_cost %lu\n", anon_cost); + seq_printf(m, "file_cost %lu\n", file_cost); } #endif diff --git a/mm/swap.c b/mm/swap.c index 49cbdb8..3486ee0 100644 --- a/mm/swap.c +++ b/mm/swap.c @@ -262,15 +262,12 @@ void rotate_reclaimable_page(struct page *page) } } -static void update_page_reclaim_stat(struct lruvec *lruvec, - int file, int rotated, - unsigned int nr_pages) +void lru_note_cost(struct lruvec *lruvec, bool file, unsigned int nr_pages) { - struct zone_reclaim_stat *reclaim_stat = &lruvec->reclaim_stat; - - reclaim_stat->recent_scanned[file] += nr_pages; - if (rotated) - reclaim_stat->recent_rotated[file] += nr_pages; + if (file) + lruvec->file_cost += nr_pages; + else + lruvec->anon_cost += nr_pages; } static void __activate_page(struct page *page, struct lruvec *lruvec, @@ -513,7 +510,7 @@ static void lru_deactivate_file_fn(struct page *page, struct lruvec *lruvec, if (active) __count_vm_event(PGDEACTIVATE); - update_page_reclaim_stat(lruvec, file, 0, hpage_nr_pages(page)); + lru_note_cost(lruvec, !file, hpage_nr_pages(page)); } static void lru_deactivate_fn(struct page *page, struct lruvec *lruvec, @@ -529,7 +526,7 @@ static void lru_deactivate_fn(struct page *page, struct lruvec *lruvec, add_page_to_lru_list(page, lruvec, lru); __count_vm_events(PGDEACTIVATE, hpage_nr_pages(page)); - update_page_reclaim_stat(lruvec, file, 0, hpage_nr_pages(page)); + lru_note_cost(lruvec, !file, hpage_nr_pages(page)); } } @@ -554,7 +551,7 @@ static void lru_lazyfree_fn(struct page *page, struct lruvec *lruvec, __count_vm_events(PGLAZYFREE, hpage_nr_pages(page)); count_memcg_page_event(page, PGLAZYFREE); - update_page_reclaim_stat(lruvec, 1, 0, hpage_nr_pages(page)); + lru_note_cost(lruvec, 0, hpage_nr_pages(page)); } } diff --git a/mm/vmscan.c b/mm/vmscan.c index 01d1a6f..b33afa3 100644 --- a/mm/vmscan.c +++ b/mm/vmscan.c @@ -1803,7 +1803,6 @@ static int too_many_isolated(struct pglist_data *pgdat, int file, static noinline_for_stack void putback_inactive_pages(struct lruvec *lruvec, struct list_head *page_list) { - struct zone_reclaim_stat *reclaim_stat = &lruvec->reclaim_stat; struct pglist_data *pgdat = lruvec_pgdat(lruvec); LIST_HEAD(pages_to_free); @@ -1832,7 +1831,8 @@ static int too_many_isolated(struct pglist_data *pgdat, int file, if (is_active_lru(lru)) { int file = is_file_lru(lru); int numpages = hpage_nr_pages(page); - reclaim_stat->recent_rotated[file] += numpages; + + lru_note_cost(lruvec, file, numpages); } if (put_page_testzero(page)) { __ClearPageLRU(page); @@ -1883,7 +1883,6 @@ static int current_may_throttle(void) isolate_mode_t isolate_mode = 0; bool file = is_file_lru(lru); struct pglist_data *pgdat = lruvec_pgdat(lruvec); - struct zone_reclaim_stat *reclaim_stat = &lruvec->reclaim_stat; bool stalled = false; while (unlikely(too_many_isolated(pgdat, file, sc))) { @@ -1910,7 +1909,6 @@ static int current_may_throttle(void) &nr_scanned, sc, isolate_mode, lru); __mod_node_page_state(pgdat, NR_ISOLATED_ANON + file, nr_taken); - reclaim_stat->recent_scanned[file] += nr_taken; if (current_is_kswapd()) { if (!cgroup_reclaim(sc)) __count_vm_events(PGSCAN_KSWAPD, nr_scanned); @@ -2061,7 +2059,6 @@ static void shrink_active_list(unsigned long nr_to_scan, LIST_HEAD(l_active); LIST_HEAD(l_inactive); struct page *page; - struct zone_reclaim_stat *reclaim_stat = &lruvec->reclaim_stat; unsigned nr_deactivate, nr_activate; unsigned nr_rotated = 0; isolate_mode_t isolate_mode = 0; @@ -2079,7 +2076,6 @@ static void shrink_active_list(unsigned long nr_to_scan, &nr_scanned, sc, isolate_mode, lru); __mod_node_page_state(pgdat, NR_ISOLATED_ANON + file, nr_taken); - reclaim_stat->recent_scanned[file] += nr_taken; __count_vm_events(PGREFILL, nr_scanned); count_memcg_events(lruvec_memcg(lruvec), PGREFILL, nr_scanned); @@ -2137,7 +2133,7 @@ static void shrink_active_list(unsigned long nr_to_scan, * helps balance scan pressure between file and anonymous pages in * get_scan_count. */ - reclaim_stat->recent_rotated[file] += nr_rotated; + lru_note_cost(lruvec, file, nr_rotated); nr_activate = move_active_pages_to_lru(lruvec, &l_active, &l_hold, lru); nr_deactivate = move_active_pages_to_lru(lruvec, &l_inactive, &l_hold, lru - LRU_ACTIVE); @@ -2288,13 +2284,13 @@ static void get_scan_count(struct lruvec *lruvec, struct scan_control *sc, { struct mem_cgroup *memcg = lruvec_memcg(lruvec); int swappiness = max(mem_cgroup_swappiness(memcg), 0); - struct zone_reclaim_stat *reclaim_stat = &lruvec->reclaim_stat; u64 fraction[2]; u64 denominator = 0; /* gcc */ struct pglist_data *pgdat = lruvec_pgdat(lruvec); unsigned long anon_prio, file_prio; enum scan_balance scan_balance; unsigned long anon, file; + unsigned long totalcost; unsigned long ap, fp; enum lru_list lru; @@ -2370,26 +2366,26 @@ static void get_scan_count(struct lruvec *lruvec, struct scan_control *sc, lruvec_lru_size(lruvec, LRU_INACTIVE_FILE, MAX_NR_ZONES); spin_lock_irq(&pgdat->lru_lock); - if (unlikely(reclaim_stat->recent_scanned[0] > anon / 4)) { - reclaim_stat->recent_scanned[0] /= 2; - reclaim_stat->recent_rotated[0] /= 2; - } - - if (unlikely(reclaim_stat->recent_scanned[1] > file / 4)) { - reclaim_stat->recent_scanned[1] /= 2; - reclaim_stat->recent_rotated[1] /= 2; + totalcost = lruvec->anon_cost + lruvec->file_cost; + if (unlikely(totalcost > (anon + file) / 4)) { + lruvec->anon_cost /= 2; + lruvec->file_cost /= 2; + totalcost /= 2; } /* * The amount of pressure on anon vs file pages is inversely - * proportional to the fraction of recently scanned pages on - * each list that were recently referenced and in active use. + * proportional to the assumed cost of reclaiming each list, + * as determined by the share of pages that are likely going + * to refault or rotate on each list (recently referenced), + * times the relative IO cost of bringing back a swapped out + * anonymous page vs reloading a filesystem page (swappiness). */ - ap = anon_prio * (reclaim_stat->recent_scanned[0] + 1); - ap /= reclaim_stat->recent_rotated[0] + 1; + ap = anon_prio * (totalcost + 1); + ap /= lruvec->anon_cost + 1; - fp = file_prio * (reclaim_stat->recent_scanned[1] + 1); - fp /= reclaim_stat->recent_rotated[1] + 1; + fp = file_prio * (totalcost + 1); + fp /= lruvec->file_cost + 1; spin_unlock_irq(&pgdat->lru_lock); fraction[0] = ap; -- 1.8.3.1